CN117829889A

CN117829889A - Power consumption information prediction method, apparatus, device, storage medium, and program product

Info

Publication number: CN117829889A
Application number: CN202311838544.0A
Authority: CN
Inventors: 李亚松; 欧东家; 张浩锋; 李帅; 廖丽娜
Original assignee: China Southern Power Grid Digital Platform Technology Guangdong Co ltd
Current assignee: China Southern Power Grid Digital Platform Technology Guangdong Co ltd
Priority date: 2023-12-28
Filing date: 2023-12-28
Publication date: 2024-04-05

Abstract

The present application relates to a power consumption information prediction method, apparatus, device, storage medium, and program product. The method comprises the following steps: acquiring first electric quantity data of a first preset duration, and inputting the first electric quantity data into a preset electric quantity prediction model. Further, the electricity consumption increase rate corresponding to the second preset duration is predicted through the electricity consumption prediction model based on the first electricity consumption data, and the whole-society electricity consumption information corresponding to the second preset duration is predicted according to the first electricity consumption data and the electricity consumption increase rate. According to the method and the device for predicting the power consumption, the power consumption increase rate obtained through prediction according to the first power consumption data and the prediction model can be used for more accurately predicting the whole-society power consumption information corresponding to the second preset duration, and therefore the accuracy of power consumption prediction can be improved.

Description

Power consumption information prediction method, apparatus, device, storage medium, and program product

Technical Field

The present application relates to the field of power systems, and in particular, to a power consumption prediction method, apparatus, device, storage medium, and program product.

Background

With the continuous improvement of the proportion of renewable energy sources, the proportion of unstable power supply in the power grid is larger and larger, and great challenges are brought to safe and stable operation of the power grid. New energy sources such as wind power, photovoltaic power generation and the like are severely changed under the influence of weather, so that the electric quantity in a power grid presents great uncertainty and randomness. Therefore, how to accurately predict the amount of power is critical to the grid system.

In the related art, the electricity consumption information change is predicted mainly by manually counting historical electricity consumption conditions, but the electricity consumption information prediction accuracy may be low.

Disclosure of Invention

In view of the foregoing, it is desirable to provide an electricity consumption information prediction method, apparatus, device, storage medium, and program product that can improve the accuracy of electricity consumption information prediction.

In a first aspect, the present application provides a method for predicting electricity consumption, the method comprising:

acquiring first electric quantity data of a first preset duration;

inputting the first electric quantity data into a preset electric quantity prediction model;

and predicting the electricity consumption increase rate corresponding to the second preset duration through an electricity consumption prediction model based on the first electricity consumption data, and predicting the whole-society electricity consumption information corresponding to the second preset duration according to the first electricity consumption data and the electricity consumption increase rate.

In one embodiment, the whole-society electricity consumption information includes whole-society electricity consumption and whole-society electricity consumption growth rate, and predicting whole-society electricity consumption information corresponding to the second preset duration according to the first electricity consumption data and the electricity consumption growth rate includes:

predicting the power consumption of the whole society through a power prediction model based on the first power consumption data and the power consumption increase rate;

And predicting the social electricity utilization increase rate through the electricity prediction model based on the first electricity consumption data and the social electricity consumption.

In one embodiment, predicting, based on the first power data, a power consumption increase rate corresponding to a second preset duration through a power prediction model includes:

determining a first predicted elasticity coefficient corresponding to the first electric quantity data;

and predicting the power consumption increase rate corresponding to the second preset duration through a power prediction model based on the first prediction elastic coefficient.

In one embodiment, the method further comprises:

acquiring second electricity consumption data of a second preset duration;

and updating the electric quantity prediction model according to the second electric quantity data, the electric quantity increase rate corresponding to the second preset time length and the whole-society electric quantity information.

In one embodiment, a training method for a preset electric quantity prediction model includes:

acquiring first historical electricity consumption data of a third preset duration;

training the initial electric quantity prediction model according to the first historical electric quantity data to obtain a preset electric quantity prediction model.

In one embodiment, the method for constructing the initial electric quantity prediction model includes:

acquiring second historical electricity consumption data and historical electricity influence factor data of a fourth preset duration;

Determining a second prediction elasticity coefficient according to the second historical electricity consumption data and the historical electricity influence factor data;

and constructing an initial electric quantity prediction model according to the second preset elastic coefficient and the second historical electric quantity data.

In one embodiment, determining the second predicted elasticity modulus based on the second historical electricity usage data and the historical electricity usage factor data includes:

dividing the second historical electricity consumption data and the historical electricity quantity influence factor data of the fourth preset time period into sub-historical electricity consumption data and sub-historical electricity quantity influence factor data of a plurality of sub-time periods;

for each sub-time period, determining the bullet performance coefficient of the sub-time period according to the sub-historical electricity consumption data and the sub-historical electricity influence factor data of the sub-time period;

and determining a second predicted elasticity coefficient according to the bullet elasticity coefficient of each sub-time period.

In a second aspect, the present application provides an electricity consumption prediction apparatus, the apparatus comprising:

the acquisition module is used for acquiring first electric quantity data of a first preset duration;

the input module is used for inputting the first electric quantity data into a preset electric quantity prediction model;

the prediction module is used for predicting the electricity consumption increase rate corresponding to the second preset duration through the electricity consumption prediction model based on the first electricity consumption data, and predicting the whole-society electricity consumption information corresponding to the second preset duration according to the first electricity consumption data and the electricity consumption increase rate.

In a third aspect, the present application provides an electricity consumption information prediction apparatus comprising a memory storing a computer program and a processor executing the computer program to perform the steps of the method of the first aspect described above.

In a fourth aspect, the present application provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method of the first aspect described above.

In a fifth aspect, the present application also provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of the method of the first aspect described above.

The electricity consumption prediction method, the electricity consumption prediction device, the electricity consumption prediction equipment, the storage medium and the program product are characterized in that first electricity consumption data of a first preset duration are obtained, and the first electricity consumption data are input into a preset electricity consumption prediction model. Further, the electricity consumption increase rate corresponding to the second preset duration is predicted through the electricity consumption prediction model based on the first electricity consumption data, and the whole-society electricity consumption information corresponding to the second preset duration is predicted according to the first electricity consumption data and the electricity consumption increase rate. Compared with the mode of predicting the electricity consumption change by manually counting the historical electricity consumption situation in the related art, the electricity consumption situation of the whole society in the preset period can be obtained by acquiring the first electricity quantity data of the first preset time period, and basic data are provided for subsequent prediction and analysis. Further, the first electric quantity data is input into the preset electric quantity prediction model, the electric quantity increase rate corresponding to the second preset duration can be accurately predicted based on the first electric quantity data, and the future electric consumption trend can be estimated more accurately by predicting the electric quantity increase rate. Further, according to the first electricity quantity data and the electricity consumption increase rate obtained by prediction of the prediction model, the whole-society electricity consumption information corresponding to the second preset duration can be predicted more accurately, and therefore the accuracy of electricity consumption prediction can be improved.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the related art, the drawings that are required to be used in the embodiments or the related technical descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to the drawings without inventive effort for a person having ordinary skill in the art.

FIG. 1 is a schematic diagram of an implementation environment of a power consumption information prediction method according to an embodiment of the present application;

FIG. 2 is a flow chart of a method for predicting electricity consumption information according to an embodiment of the present application;

FIG. 3 is a flowchart illustrating a method for predicting electricity consumption information according to another embodiment of the present disclosure;

FIG. 4 is a flowchart illustrating a method for predicting electricity consumption information according to another embodiment of the present disclosure;

FIG. 5 is a flowchart illustrating a method for predicting electricity consumption information according to another embodiment of the present disclosure;

FIG. 6 is a flowchart illustrating a method for predicting power consumption information according to another embodiment of the present disclosure;

FIG. 7 is a flowchart illustrating a method for predicting electricity consumption information according to another embodiment of the present disclosure;

FIG. 8 is a schematic overall flow chart of a method for predicting electricity consumption information according to an embodiment of the present application;

FIG. 9 is a schematic structural diagram of an electricity consumption information prediction device according to an embodiment of the present application;

fig. 10 is an internal structural diagram of the electricity information prediction apparatus in one embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.

The power consumption information prediction method, the device, the equipment, the storage medium and the program product provided by the embodiment of the application can be applied to the application scene of power consumption information prediction; of course, the method can also be applied to other scenes, and the embodiment of the application is not limited to this.

In the related art, the electricity consumption change is predicted mainly by manually counting historical electricity consumption conditions. However, in this way, rapid fluctuations in the grid load containing a large amount of new energy cannot be accommodated, resulting in lower accuracy of the prediction results. Further, if the electricity consumption prediction result is inaccurate, the power grid system cannot perform reasonable and effective economic dispatching in advance according to the prediction result, a large amount of electricity dispatching blindness may be caused, peak shaving cost is too high, serious electricity gap or surplus problems can occur, and safe and stable operation of the power grid is severely restricted and threatened. Thus, accurately predicting the amount of electricity usage is critical to the grid system.

FIG. 1 is a schematic diagram of an implementation environment of a method for predicting electricity consumption information according to an embodiment of the present application, as shown in FIG. 1, where the implementation environment may include: a terminal 101 and a server 102. The terminal 101 may communicate with the server 102 through a network, and the terminal 101 may include, but is not limited to, various personal computers, notebook computers, smart phones, and tablet computers. The server 102 may be implemented as a stand-alone server or as a server cluster of multiple servers. The data storage system may store first power data of a first preset duration, a preset power prediction model, a power consumption increase rate corresponding to a second preset duration, and the like, which are required to be processed by the server 102. The data storage system may be integrated on the server 102 or may be located on a cloud or other network server.

In combination with the implementation environment shown in fig. 1, in the embodiment of the present application, the electricity consumption prediction device may be a server 102, where the server 102 may obtain first electricity quantity data of a first preset duration, and input the first electricity quantity data into a preset electricity quantity prediction model. Further, the server 102 predicts an electricity consumption rate corresponding to the second preset duration through an electricity consumption prediction model based on the first electricity consumption data, and predicts the whole-society electricity consumption information corresponding to the second preset duration according to the first electricity consumption data and the electricity consumption rate. Further, the server 102 may send the predicted social electricity information corresponding to the second preset duration to the terminal 101.

It should be understood that the electricity consumption information prediction device may also be a terminal 101, and the terminal 101 may be a terminal corresponding to a power grid person. The terminal 101 may acquire first power data of a first preset duration, and input the first power data into a preset power prediction model. Further, the terminal 101 predicts an electricity consumption rate corresponding to the second preset duration through an electricity consumption prediction model based on the first electricity consumption data, and predicts whole-society electricity consumption information corresponding to the second preset duration according to the first electricity consumption data and the electricity consumption rate.

In order to solve the problem of low electricity consumption prediction accuracy in the related art, the electricity consumption prediction method, the device, the equipment, the storage medium and the program product provided by the embodiment of the application can obtain the electricity consumption condition of the whole society in a preset period by acquiring the first electricity consumption data of a first preset duration, and provide basic data for subsequent prediction and analysis. The first electric quantity data is input into a preset electric quantity prediction model, the power consumption increase rate corresponding to the second preset time length can be accurately predicted based on the first electric quantity data, and the future power consumption trend can be estimated more accurately by predicting the power consumption increase rate. Further, according to the first electricity quantity data and the electricity consumption increase rate obtained by prediction of the prediction model, the whole-society electricity consumption information corresponding to the second preset duration can be predicted more accurately, and therefore the accuracy of electricity consumption prediction can be improved.

In one embodiment, fig. 2 is a schematic flow chart of a method for predicting electricity consumption information in one embodiment of the present application, where the embodiment of the present application is described by taking an application of the method to an electricity consumption information prediction device as an example, where the electricity consumption information prediction device may include, but is not limited to, a terminal or a server. As shown in fig. 2, the method of the embodiments of the present application may include the following steps.

Step S201, acquiring first electric quantity data of a first preset duration.

Illustratively, the first electricity amount data referred to in the embodiments of the present application is used to indicate an electricity amount curve regarding time-electricity amount data generated from historical social electricity amounts for a preset time.

For example, the electricity consumption prediction device in the embodiment of the present application may directly receive electricity consumption data sent by other devices; or the electricity consumption prediction device directly acquires the collected electricity consumption data from the power grid system. The electricity consumption data entry information may include, but is not limited to, area names, year, spontaneous electricity consumption, power plant electricity consumption, and the like. It should be understood that the sum of the spontaneous electricity consumption and the power plant electricity consumption corresponds to the electricity consumption of the whole society.

In this step, the electricity consumption prediction device may obtain the electricity consumption of the whole society within the preset period accurately by obtaining the historical electricity consumption data of the whole society for the first preset period (for example, the past 6 months or the past 5 years, etc.), and provide the basic data for the subsequent prediction and analysis.

Step S202, input the first electric quantity data into a preset electric quantity prediction model.

The preset power prediction model in the embodiment of the present application refers to a mathematical model or algorithm for predicting power change, and predicts power conditions within a certain period of time by inputting first power data. The specific model may be based on statistical methods, machine learning, deep learning, or other predictive techniques.

In a possible implementation manner, in the embodiment of the present application, a power consumption curve of the generated time-power data may be preprocessed, so as to obtain a power consumption curve of the processed time-power data, and the power consumption curve is input into a preset power prediction model; in order to eliminate noise, extract trends or improve data quality. The preprocessing may include, but is not limited to, filtering, smoothing, etc.

In another possible implementation manner, the electricity consumption curve of the generated time-electricity data in the embodiment of the present application is directly input to the preset electricity prediction model without any processing.

In this step, the electricity consumption prediction device may input the first electricity consumption data into the preset electricity consumption prediction model according to the first electricity consumption data, so that the subsequent predicted electricity consumption information may be accurately obtained, and the electricity consumption rule and trend may be captured more accurately, thereby improving the accuracy of prediction.

Step S203, a power consumption increase rate corresponding to a second preset duration is predicted through a power prediction model based on the first power consumption data, and whole-society power consumption information corresponding to the second preset duration is predicted according to the first power consumption data and the power consumption increase rate.

Illustratively, the second preset time period referred to in the embodiment of the present application refers to a preset time period for predicting the amount of electricity used for a future period of time.

Illustratively, the electricity consumption rate referred to in the embodiments of the present application is used to indicate the rate of increase of future electricity consumption of the reference area predicted by the prediction model based on the first electricity consumption data.

By way of example, the social electricity usage information referred to in embodiments of the present application may include, but is not limited to, social electricity usage and social electricity usage growth rate. The total electricity consumption of the whole society is the total electricity consumption of the whole society, and various electricity sources such as families, industries, businesses and the like are covered. The rate of increase of electricity consumption of the whole society is the rate of change of electricity consumption of the whole society, and represents the rate of increase of the total amount of electricity consumption of the whole society in a certain period of time.

In this step, the electricity consumption prediction device may more accurately predict the electricity consumption situation of a certain area in a future period of time by deducing the electricity consumption increase rate of the second preset period of time based on the first electricity consumption data and the prediction model. Further, the electricity consumption prediction device can more accurately predict the electricity consumption information of the whole society according to the electricity consumption condition of a certain area and the first electricity consumption data in a future period of time through an electricity consumption prediction model, so that the distribution and management of energy resources can be planned better to cope with possible future demand fluctuation, and the resource utilization efficiency is improved.

In the electricity consumption prediction method, the electricity consumption prediction device obtains first electricity quantity data of a first preset duration and inputs the first electricity quantity data into a preset electricity quantity prediction model. Further, the electricity consumption prediction device predicts an electricity consumption increase rate corresponding to the second preset duration through an electricity consumption prediction model based on the first electricity consumption data, and predicts the whole-society electricity consumption information corresponding to the second preset duration according to the first electricity consumption data and the electricity consumption increase rate. In the embodiment of the application, the electricity consumption prediction device can obtain the electricity consumption condition of the whole society in the preset period by acquiring the first electricity consumption data of the first preset period, and provides basic data for subsequent prediction and analysis. The first electric quantity data is input into a preset electric quantity prediction model, the electric quantity increase rate corresponding to the second preset duration can be accurately predicted by the electric quantity prediction equipment based on the first electric quantity data, and the future electric consumption trend can be estimated more accurately by predicting the electric quantity increase rate. Further, according to the first electricity quantity data and the electricity consumption increase rate obtained by prediction of the prediction model, the whole-society electricity consumption information corresponding to the second preset duration can be predicted more accurately, and therefore the accuracy of electricity consumption prediction can be improved.

In an embodiment, fig. 3 is a schematic flow chart of a method for predicting electricity consumption information according to another embodiment of the present application, and in this embodiment of the present application, description is given, by way of example, of related content of "all-society electricity consumption information corresponding to predicting a second preset duration according to the first electricity consumption data and the electricity consumption increase rate" in step S203 related to the foregoing embodiment. The method of the embodiment of the application can comprise the following steps.

Step S2031, predicting the power consumption of the whole society through a power prediction model based on the first power consumption data and the power consumption increase rate.

Illustratively, the total social electricity consumption referred to in the embodiments of the present application is used to indicate the total social electricity consumption, and covers various sources of electricity, such as home, industry, business, etc.

Optionally, the electricity consumption prediction device may determine the total social electricity consumption of the first preset duration according to the first electricity consumption data of the first preset duration. For example, the electricity consumption prediction device may sum each of the electricity consumption data within the first preset time period to obtain the total social electricity consumption of the first preset time period. For another example, the electricity consumption prediction device may determine the total social electricity consumption of the first preset duration according to the first electricity consumption data of the first preset duration using a time sequence analysis method. The method can infer electricity consumption in a future period by analyzing trends, seasonality and periodicity of historical electricity consumption data.

In the step, the electricity consumption prediction device can accurately predict and obtain the electricity consumption of the whole society corresponding to the second preset duration through the electricity consumption prediction model based on the electricity consumption of the whole society corresponding to the first preset duration and the electricity consumption increase rate of the reference area, and is beneficial to the user to make future energy supply and demand planning according to the predicted electricity consumption of the whole society.

In a possible implementation manner, a formula for predicting the electricity consumption of the whole society in the electricity consumption prediction model according to the embodiment of the present application may be expressed as:

（1）

wherein,the unit of the full-society electricity consumption corresponding to the second preset time length can be hundred million kWh; />The unit of the full-society electricity consumption for the first preset time length can be hundred million kWh; />Is a first coefficient, obtained from historical experience, optionally,>may be 1; />Is the power consumption increase rate.

Of course, the formula for predicting the total social electricity consumption may be expressed as other variations of the above formula (1) or an equivalent formula.

In another possible implementation manner, the electric quantity prediction model in the embodiment of the present application may include a first sub-electric quantity prediction model, and the electric consumption prediction device may input the total social electric quantity corresponding to the first preset duration and the electric quantity increase rate of the reference area into the first sub-electric quantity prediction model, so as to obtain the total social electric quantity corresponding to the second preset duration output by the first sub-electric quantity prediction model. The first sub-electric quantity prediction model may be a neural learning model or a machine learning model.

Step S2032, predicts a social electricity usage growth rate through an electricity prediction model based on the first electricity consumption data and the social electricity consumption.

Illustratively, the rate of increase of the total social electricity consumption referred to in the embodiments of the present application refers to the rate of change of the total social electricity consumption, and represents the rate of increase of the total amount of total social electricity consumption over a certain period of time.

In the step, the electricity consumption prediction device can further obtain the electricity consumption growth rate of the whole society corresponding to the second preset duration through the electricity consumption prediction model based on the electricity consumption of the whole society corresponding to the first preset duration and the electricity consumption of the whole society corresponding to the second preset duration, and can better know the trend of the electricity consumption of the society through obtaining the electricity consumption growth rate of the whole society, so that the analysis of the trend of the electricity consumption of the society is facilitated, and the trend analysis is vital for long-term planning and decision making.

In one possible implementation manner, a formula for predicting a power consumption growth rate of the whole society in the power prediction model according to the embodiment of the present application may be expressed as:

（2）

wherein,the power consumption increase rate of the whole society corresponding to the second preset time length; />Is a second coefficient, obtained from historical experience, optionally,>may be 1; />Is a third coefficient, obtained from historical experience, optionally, >May be 100.

Of course, the formula for predicting the rate of increase of electricity consumption in the whole society can be expressed as other variations of the above formula (2) or an equivalent formula.

In another possible implementation manner, the electric quantity prediction model in the embodiment of the present application may include a second sub-electric quantity prediction model, and the electric consumption prediction device may input the total social electric quantity corresponding to the first preset duration and the total social electric quantity corresponding to the second preset duration into the second sub-electric quantity prediction model, so as to obtain the total social electric consumption growth rate corresponding to the second preset duration output by the second sub-electric quantity prediction model. The second sub-electric quantity prediction model may be a neural learning model or a machine learning model.

By way of example, the embodiment of the application can predict the whole-society electricity consumption information through the electricity consumption prediction model and display the whole-society electricity consumption information, the change rate of the whole-society electricity consumption and other information on the terminal where the user is located through the visual interface, so that the user can visually check and analyze the information conveniently.

In the embodiment of the application, the electricity consumption prediction device can accurately predict and obtain the electricity consumption of the whole society through the electricity consumption prediction model based on the first electricity consumption data and the electricity consumption increase rate of a certain area. Further, the electricity consumption prediction device can further obtain the electricity consumption growth rate of the whole society based on the first electricity consumption data and the predicted electricity consumption of the whole society, and the trend of the electricity consumption of the society can be better known by obtaining the electricity consumption growth rate of the whole society, so that the electricity consumption prediction device is beneficial to a user to make future energy supply and demand planning according to the predicted electricity consumption of the whole society.

In an embodiment, fig. 4 is a schematic flow chart of a method for predicting electricity consumption information according to another embodiment of the present application, which is based on the above embodiment, and in the embodiment of the present application, the relevant content of "predicting, by a electricity prediction model, an electricity consumption increase rate corresponding to a second preset duration based on first electricity data" in step S203 related to the above embodiment is described as an example. The method of the embodiment of the application can comprise the following steps.

In step S401, a first predicted elasticity coefficient corresponding to the first electric quantity data is determined.

Illustratively, the first predicted elasticity coefficient referred to in the embodiments of the present application is an index indicating the sensitivity or the response degree of the power consumption amount change calculated from the first power consumption amount data.

Hereinafter, an exemplary description will be given of a manner of determining the first predicted elastic modulus in the embodiments of the present application.

In one possible implementation, the electricity consumption prediction device may obtain the first predicted elastic coefficient according to historical experience.

In another possible implementation manner, the electricity consumption prediction device may determine the first predicted elastic coefficient according to the first electric quantity data of the first preset duration and the corresponding electric quantity influence factor data, and the detailed process refers to the related content in step S702.

In this step, the electricity consumption prediction device may obtain the corresponding first prediction elastic coefficient according to the first electricity amount data. Therefore, in the embodiment of the application, the change trend of the electric quantity can be effectively predicted by calculating the prediction elastic coefficient, so that a user is helped to make reasonable electricity utilization arrangement and decision.

Step S402, a power consumption increase rate corresponding to a second preset duration is predicted through a power prediction model based on the first prediction elastic coefficient.

In a possible implementation manner, a formula for predicting a power consumption increase rate in the power consumption prediction model according to the embodiment of the present application may be expressed as:

（3）

wherein,the power consumption increase rate corresponding to the second preset duration is set; />Is the first predicted elastic coefficient; />And predicting according to historical experience or a corresponding prediction model to obtain the preset economic growth rate.

Of course, the formula of predicting the electricity consumption rate may also be expressed as other variations of the above formula (3) or an equivalent formula.

In another possible implementation manner, the electric quantity prediction model in the embodiment of the present application may include a third sub-electric quantity prediction model, and the electricity consumption prediction device may input the first prediction elastic coefficient and the preset economic growth rate into the third sub-electric quantity prediction model, so as to obtain an electricity consumption growth rate corresponding to a second preset duration output by the third sub-electric quantity prediction model. The third sub-electric quantity prediction model may be a neural learning model or a machine learning model.

In the step, the electricity consumption prediction device can accurately obtain the electricity consumption increase rate corresponding to the second preset duration through the electricity consumption prediction model based on the first prediction elastic coefficient, and further can more accurately predict the electricity consumption information of the whole society through predicting the electricity consumption increase rate of a certain area, thereby providing a favorable support for the follow-up prediction of the electricity consumption information of the whole society.

In the embodiment of the application, the electricity consumption prediction device can know the correlation between the electric quantity and other factors by calculating the first prediction elastic coefficient, can effectively predict the change trend of the electric quantity, and helps users to make reasonable electricity consumption arrangement and decision. Further, the electricity consumption prediction device can accurately obtain the electricity consumption increase rate corresponding to the second preset duration through the electricity consumption prediction model based on the calculated first prediction elastic coefficient, and can effectively predict the change trend of the electricity consumption through predicting the electricity consumption increase rate of a certain area so as to help users to make reasonable electricity consumption arrangement and decision.

In an embodiment, based on the foregoing embodiment, fig. 5 is a schematic flow chart of a method for predicting electricity consumption information according to another embodiment of the present application, where relevant content of an update manner of the "electricity consumption prediction model" related to the foregoing embodiment is described and illustrated by way of example. The method of the embodiment of the application can comprise the following steps.

Step S501, obtaining second power consumption data of a second preset duration.

The second electricity consumption data in the embodiment of the present application refers to electricity consumption data in a preset duration acquired in real time.

In the step, the electricity consumption prediction device can acquire electricity consumption data in a preset time period in real time, and input the electricity consumption data into the electricity consumption prediction model so as to obtain predicted electricity consumption data in a future time period.

Step S502, updating the electricity quantity prediction model according to the second electricity quantity data, the electricity quantity increase rate corresponding to the second preset time length and the whole society electricity consumption information.

In this step, the electricity consumption prediction device may obtain the second electricity consumption data in real time, and compare the second electricity consumption data obtained in real time with the electricity consumption increase rate and the whole society electricity consumption information corresponding to the second preset duration predicted by the electricity consumption prediction model, so as to adjust parameters (for example, the first prediction elastic coefficient, the preset economic increase rate, the first coefficient, the second coefficient, etc.) of the electricity consumption prediction model.

In a possible implementation manner, the electricity consumption prediction device may determine an actual electricity consumption increase rate and an actual social electricity consumption increase rate according to the second electricity consumption data acquired in real time; further, the electricity consumption prediction device compares the actual electricity consumption increase rate and the actual social electricity consumption increase rate with the predicted electricity consumption increase rate and the actual social electricity consumption increase rate respectively, and accordingly adjusts the model according to whether thresholds between the prediction results and the actual results meet preset thresholds.

In another possible implementation manner, the electricity consumption prediction device may determine actual social electricity consumption data according to the second electricity consumption data obtained in real time; further, the electricity consumption prediction device compares the actual whole-society electricity consumption data with the predicted whole-society electricity consumption data, and accordingly adjusts the model according to whether a threshold between a prediction result and an actual result meets a preset threshold.

Therefore, in the embodiment of the application, the prediction effect of the model is evaluated by analyzing and comparing the prediction result and the actual result of the electric quantity prediction model, so that the online continuous learning of the electric quantity prediction model is realized, and the sensitivity and the adaptability to the electric quantity change rule are maintained.

In an embodiment, based on the foregoing embodiment, fig. 6 is a schematic flow chart of a power consumption information prediction method according to another embodiment of the present application, where relevant content of a training method of a "preset power consumption prediction model" is described and illustrated by way of example. The method of the embodiment of the application can comprise the following steps.

Step S601, acquiring first historical power consumption data of a third preset duration.

Illustratively, the first historical electricity consumption data referred to in the embodiment of the present application refers to obtaining actual electricity consumption data within a past preset period of time.

In the step, the electricity consumption prediction device obtains the historical actual electricity consumption data in a period of time so as to train the electricity consumption prediction model better later.

Step S602, training the initial electric quantity prediction model according to the first historical electric quantity data to obtain a preset electric quantity prediction model.

Illustratively, the initial power model referred to in the embodiments of the present application refers to an initially established mathematical model or algorithm for predicting power changes.

Optionally, in the embodiment of the present application, the electricity consumption prediction device may divide the first historical electricity consumption data of the third preset duration into two phases, input the historical electricity consumption data of the previous phase into the initial electricity consumption model, and predict the historical electricity consumption data of the next phase.

In a possible implementation manner, in the embodiment of the present application, the historical power consumption data of the previous stage may be preprocessed to obtain the processed historical power consumption data of the previous stage, and the processed historical power consumption data of the previous stage is input to the initial power prediction model; in order to eliminate noise, extract trends or improve data quality. The preprocessing may include, but is not limited to, filtering, smoothing, etc.

In another possible implementation manner, the historical electricity consumption data of the previous stage in the embodiment of the present application is directly input to the initial electricity model without any processing.

In this step, the electricity consumption prediction device may input the historical electricity consumption data of the previous stage into the initial electricity consumption model, and predict the historical electricity consumption data of the next stage by using the initial electricity consumption model. Further, comparing and analyzing the predicted historical power consumption data of the later stage with the actual historical power consumption data of the later stage, and continuously optimizing parameters in the initial power model by using an iterative algorithm until a threshold between the predicted historical power consumption number and the actual historical power consumption data meets a preset threshold, so that a preset power prediction model is obtained.

For example, assume that the electricity usage prediction device acquires first historical electricity usage data between 2018-2022, and divides the first historical electricity usage data between 2018-2022 into two phases, respectively, historical electricity usage data of 2018-2020 and historical electricity usage data of 2021-2022. The historical power usage data for 2018-2020 is entered into the initial power model, and the historical power usage data for 2021-2022 is predicted. Further, by comparing the predicted historical electricity consumption data of 2021-2022 with the actual historical electricity consumption data of 2021-2022, the parameters in the initial electricity consumption model are continuously optimized by using an iterative algorithm, so that a preset electricity consumption prediction model is obtained.

Therefore, in the embodiment of the application, the power consumption information prediction device divides the first historical power consumption data into two stages, and uses the real historical data to continuously train the model, so that the initial power model can better adapt to the change characteristics of the historical power consumption data, and the prediction accuracy of the preset power consumption prediction model can be improved.

In the embodiment of the application, the electricity consumption prediction device obtains the historical actual electricity consumption data in a period of time so as to train the electricity consumption prediction model better later. Further, the electricity consumption prediction device divides the first historical electricity consumption data into two stages, and uses the real historical data to continuously train the model, so that the initial electricity consumption model can better adapt to the change characteristics of the historical electricity consumption data, and the prediction accuracy of the preset electricity consumption prediction model can be improved.

In one embodiment, fig. 7 is a schematic flow chart of a method for predicting electricity consumption information according to another embodiment of the present application, where the relevant content of the method for constructing the "initial electricity consumption prediction model" is described in an exemplary manner. The method of the embodiment of the application can comprise the following steps.

Step S701, obtaining second historical power consumption data and historical power influence factor data of a fourth preset duration.

By way of example, the historical power influencing factors in the embodiments of the present application refer to that the reference area has different factors influencing the change of the historical power within a preset period of time. For example, historical influencing factors may include, but are not limited to, electricity prices for a preset period of time, electricity demand for a period of time, average temperature, population density.

In this step, the electricity consumption prediction device may obtain the historical electricity consumption data within the preset duration and various factors affecting the change of the historical electricity consumption data, so as to provide a real data base for the subsequent operation.

Step S702, determining a second predicted elasticity coefficient according to the second historical power consumption data and the historical power influence factor data.

Illustratively, the second predicted elasticity coefficient referred to in the embodiments of the present application is an index indicating the sensitivity or the response degree of various factors affecting the power change to the power consumption change.

In this step, the electricity consumption prediction device may calculate a second predicted elastic coefficient according to the second electricity consumption data and the historical electricity consumption influence factor data.

Therefore, in the embodiment of the application, by calculating the second prediction elasticity coefficient, the correlation between the electric quantity and other factors can be known, prediction is performed according to the correlation, the change trend of the electric quantity can be effectively predicted, and a user is helped to make reasonable electricity utilization arrangement and decision.

Hereinafter, description will be given exemplarily to the content related to determining the second elastic coefficient.

In a possible implementation manner, the second historical power consumption data and the historical power influence factor data of the fourth preset duration are divided into sub-historical power consumption data and sub-historical power influence factor data of a plurality of sub-time periods.

In this step, it is considered that the historical electricity consumption amount data and the historical electricity consumption amount influence factor data may show different patterns or trends in different time periods. Therefore, the electricity consumption information prediction apparatus may divide the second historical electricity consumption amount data and the historical electricity consumption amount influence factor data of the fourth preset duration into the sub-historical electricity consumption amount data and the sub-historical electricity consumption amount influence factor data of the plurality of sub-time periods.

For example, assuming that the fourth preset time period is one year, the electricity consumption prediction apparatus may divide the data of one year into four quarters, each quarter being one sub-period, that is, including sub-period 1, sub-period 2, sub-period 3, and sub-period 4. And extracting corresponding sub-historical power consumption data and sub-historical power influence factor data for each sub-time period. For example, for sub-time period 1, the sub-historical electricity usage data is 1000 kWh, and the sub-historical electricity usage factor data is average temperature, population density, and the like. For the sub-time period 2, the sub-historical electricity consumption data is 1200kWh, and the sub-historical electricity influence factor data is the electricity price and the electricity demand of the duration.

Further, for each sub-period, determining a sub-elasticity coefficient of the sub-period according to the sub-historical electricity consumption data and the sub-historical electricity influence factor data of the sub-period.

Illustratively, the bullet-shaped coefficient referred to in the embodiments of the present application represents the sensitivity or degree of response of the charge to the influencing factor over a particular period of time.

Illustratively, the calculation formula of the bullet-performance coefficient referred to in the embodiments of the present application can be expressed as:

（4）

wherein,the change quantity of the historical electric quantity influence factor data in the time period of T1-T2 is obtained; />Is the bullet coefficient of elasticity in the period of T1-T2; />Is the historical electricity consumption in the time period of T1-T2According to the amount of change.

Of course, the formula of the bullet-susceptibility coefficient may also be expressed as other variations of the above formula (4) or as an equivalent formula.

In this step, for each sub-period, the electricity consumption prediction apparatus calculates a bullet performance coefficient using the sub-historical electricity consumption data and the sub-historical electricity consumption influence factor data. Therefore, the relation between the electric quantity and each factor in different time periods can be understood more finely by determining the bullet coefficient of the sub-time period according to the sub-historical electric quantity data and the sub-historical electric quantity influence factor data of the sub-time period, and the accuracy of subsequent prediction is improved.

Further, a second predicted elasticity coefficient is determined based on the bullet elasticity coefficients for each sub-period.

Illustratively, the calculation formula of the second predicted elasticity coefficient referred to in the embodiment of the present application may be expressed as:

（5）

wherein T is a second predicted elastic coefficient;is the bullet coefficient of elasticity in the period of T2-T3; t (T) _n Is the bullet coefficient of elasticity in the period of T (n) -T (n+1); />Is a weight coefficient.

Of course, the formula of the second predicted elastic modulus may also be expressed as other variations of the above formula (5) or as an equivalent formula.

In this step, the electricity consumption prediction device may calculate, according to the bullet coefficient of each sub-period, a second predicted elastic coefficient in a preset manner. In this way, the electricity consumption prediction device is facilitated to obtain a more comprehensive predicted elasticity coefficient for the whole second historical electricity consumption data and the historical electricity consumption influence factor data.

Illustratively, the preset manner may include, but is not limited to, weighting the sub-elasticity coefficients, other integration methods.

In another possible implementation manner, the electric quantity prediction model in the embodiment of the present application may include a fourth sub-electric quantity prediction model, and the electricity consumption prediction device may input second historical electric quantity data and historical electric quantity influence factor data into the fourth sub-electric quantity prediction model, so as to obtain a second prediction elasticity coefficient output by the fourth sub-electric quantity prediction model. The fourth sub-electric quantity prediction model may be a neural learning model or a machine learning model.

In the embodiment of the application, the power consumption information prediction device can capture the dynamic relation between the electric quantity and each influence factor more accurately by dividing the molecular time period and calculating the bullet coefficient, and is favorable for revealing the law of electric quantity change on a time scale with finer granularity, so that the accuracy of prediction is improved. The electricity consumption prediction device can make a reasonable decision by knowing the relation between the electric quantity and the influence factors in different time periods and making an electricity consumption strategy more pertinently by a user.

Step S703, constructing an initial power prediction model according to the second preset elastic coefficient and the second historical power consumption data.

In this step, the electricity consumption prediction device may construct an initial electricity consumption prediction model according to the calculated second preset elastic coefficient and the obtained second historical electricity consumption data. Therefore, the electricity consumption prediction device constructs an initial prediction model by considering the historical electricity consumption data and the historical electricity consumption influence factor data, provides basic prediction for future electricity consumption change, can better understand the trend and rule of the electricity consumption change, and is beneficial to making more intelligent electricity consumption arrangement and decision.

In a possible implementation manner, the initial prediction model in the embodiment of the present application includes, but is not limited to, the formula (1) -the formula (5) in the above embodiment.

In another possible implementation manner, the initial prediction model in the embodiment of the present application may include, but is not limited to, the first sub-power prediction model, the second sub-power prediction model, the third sub-power prediction model, and the fourth sub-power prediction model in the above embodiment.

In the embodiment of the application, the electricity consumption prediction device can provide a real data basis for subsequent operations by acquiring the historical electricity consumption data in the preset time period and various factors influencing the change of the historical electricity consumption data. Further, the electricity consumption prediction device can know the correlation between the electric quantity and other factors by calculating the second prediction elastic coefficient, and predict according to the correlation, so that the change trend of the electric quantity can be effectively predicted. Further, the electricity consumption prediction device constructs an initial prediction model by considering the historical electricity consumption data and the historical electricity consumption influence factor data, provides basic prediction for future electricity consumption change, can better understand the trend and rule of the electricity consumption change, and is helpful for making more intelligent electricity consumption arrangement and decision.

In one embodiment, fig. 8 is an overall flow chart of the electricity consumption information prediction method in one embodiment of the present application based on the above embodiment. As shown in fig. 8, the method may include the following steps.

(1) The electricity consumption information prediction device may acquire second historical electricity consumption data and historical electricity consumption influence factor data of a fourth preset duration.

(2) The electricity consumption prediction device preprocesses the second historical electricity consumption data to obtain the processed second historical electricity consumption data so as to eliminate noise, extract trend or improve data quality. The preprocessing may include, but is not limited to, filtering, smoothing, etc.

(3) The electricity consumption prediction device determines a second prediction elasticity coefficient according to the second historical electricity consumption data and the historical electricity consumption influence factor data.

(4) And the electricity consumption prediction equipment constructs an initial electricity consumption prediction model according to the second preset elastic coefficient and the second historical electricity consumption data.

(5) The power consumption information prediction device trains the initial power consumption prediction model.

The electricity consumption prediction equipment acquires first historical electricity consumption data of a third preset duration; further, the electricity consumption prediction device trains the initial electricity consumption prediction model according to the first historical electricity consumption data, and the iteration algorithm is used for continuously optimizing parameters in the initial electricity consumption model until a threshold between the predicted historical electricity consumption number and the actual historical electricity consumption data meets a preset threshold, so that the preset electricity consumption prediction model is obtained.

(6) The electricity consumption prediction equipment acquires first electric quantity data of a first preset duration.

The power consumption prediction device in the embodiment of the present application may perform preprocessing on a power consumption curve of the first power consumption data to obtain the processed first power consumption data.

(7) The electricity consumption prediction device obtains predicted whole-society electricity consumption information by inputting the first electricity consumption data into a preset electricity consumption prediction model.

It should be noted that, the realizable manner and the technical effect of each step in the embodiments of the present application may refer to the relevant content in the above embodiments, which is not repeated herein.

In summary, in the embodiment of the foregoing application, the electricity consumption prediction device obtains first electricity quantity data of a first preset duration, and inputs the first electricity quantity data into a preset electricity quantity prediction model. Further, the electricity consumption prediction device predicts an electricity consumption increase rate corresponding to the second preset duration through an electricity consumption prediction model based on the first electricity consumption data, and predicts the whole-society electricity consumption information corresponding to the second preset duration according to the first electricity consumption data and the electricity consumption increase rate. Through evaluation verification on the preset electric quantity prediction model, the following effects are achieved in the embodiment of the application. (1) The prediction result of the method can keep at least 95% average fitness with the actual electric quantity curve when tested in a power grid with a new energy accounting ratio of 30%, and the prediction error can be controlled within 5%, so that the accurate scheduling requirement is met. Compared with 75% accuracy of the traditional prediction method, the prediction accuracy of the embodiment of the application is improved by at least 20%. (2) The training and prediction calculation process of the preset electric quantity prediction model adopts a parallel architecture, and the running speed is improved by at least 30% compared with that of the prior serial model. (3) When the new energy source ratio is increased to 45%, the predictive fitness of the preset electric quantity predictive model still can reach at least 90%. (4) The preset electric quantity prediction model supports learning and updating, can be deeply fused with a smart power grid, and realizes self-adaption, self-optimization and self-treatment of the power grid. Therefore, the prediction model technology of the preset electric quantity can remarkably improve the prediction capability of the rapid change electric quantity in the new energy grid-connected power grid, so that the power grid system can be more safely and efficiently scheduled, and the prediction model technology of the preset electric quantity has important value for promoting the large-scale new energy consumption and guaranteeing the full-quantity grid connection of the renewable energy sources.

It should be understood that, although the steps in the flowcharts related to the above embodiments are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.

Based on the same inventive concept, the embodiment of the application also provides an electricity consumption prediction device for realizing the above related electricity consumption prediction method. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in the embodiments of the electricity consumption prediction device or devices provided below may refer to the limitation of the electricity consumption prediction method hereinabove, and will not be repeated here.

In an embodiment, fig. 9 is a schematic structural diagram of an electricity consumption information prediction apparatus in an embodiment of the present application, where the electricity consumption information prediction apparatus provided in the embodiment of the present application may be applied to an electricity consumption information prediction device, and the electricity consumption information prediction device may be a terminal or a server. As shown in fig. 9, the electricity consumption prediction apparatus according to the embodiment of the present application may include: a first acquisition module 901, an input module 902, and a prediction module 903, wherein:

a first obtaining module 901, configured to obtain first electric quantity data of a first preset duration;

the input module 902 is configured to input a preset electric quantity prediction model according to the first electric quantity data;

the prediction module 903 is configured to predict, based on the first electricity quantity data, an electricity consumption increase rate corresponding to a second preset duration through an electricity quantity prediction model, and predict, according to the first electricity quantity data and the electricity consumption increase rate, all-society electricity consumption information corresponding to the second preset duration.

In one embodiment, the social electricity consumption information includes social electricity consumption and social electricity consumption growth rate, and the prediction module 903 is configured to:

In one embodiment, the prediction module 903 is further configured to:

In an embodiment, the electricity consumption prediction apparatus further includes a second acquisition module and an update module, where:

the second acquisition module is used for acquiring second electricity consumption data of a second preset duration;

and the updating module is used for updating the electric quantity prediction model according to the second electric quantity data, the electric quantity increase rate corresponding to the second preset duration and the whole-society electric quantity information.

In an embodiment, the electricity consumption prediction apparatus further includes a third acquisition module and a training module, where:

the third acquisition module is used for acquiring first historical electricity consumption data of a third preset duration;

and the training module is used for training the initial electric quantity prediction model according to the first historical electric quantity data to obtain a preset electric quantity prediction model.

In one embodiment, the training module includes an acquisition unit, a determination unit, and a construction module, where:

The acquisition unit is used for acquiring second historical electricity consumption data and historical electricity influence factor data of a fourth preset duration;

the determining unit is used for determining a second prediction elasticity coefficient according to the second historical electricity consumption data and the historical electricity influence factor data;

the construction module is used for constructing an initial electric quantity prediction model according to the second preset elastic coefficient and the second historical electric quantity data.

In an embodiment, the determining unit is specifically configured to:

The power consumption information prediction device provided in this embodiment may execute the above method embodiment, and its implementation principle and technical effects are similar, and will not be described herein.

The above-described respective modules in the electricity consumption information prediction apparatus may be implemented in whole or in part by software, hardware, and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the electricity consumption information prediction device, or may be stored in software in a memory in the electricity consumption information prediction device, so that the processor may invoke and execute operations corresponding to the above modules.

In an exemplary embodiment, there is provided an electricity consumption information prediction apparatus, which may be a server or a terminal, and an internal structure diagram thereof may be as shown in fig. 10. The electricity consumption prediction device comprises a processor, a memory, an Input/Output interface (I/O) and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the electricity consumption prediction device is configured to provide computing and control capabilities. The memory of the electricity consumption prediction device includes a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the electricity consumption prediction device is used for storing first electricity consumption data of a first preset duration to be processed, a preset electricity consumption prediction model, an electricity consumption increase rate corresponding to a second preset duration and the like. The input/output interface of the electricity consumption prediction device is used for exchanging information between the processor and the external device. The communication interface of the electricity consumption prediction device is used for communicating with an external terminal through network connection. The computer program, when executed by a processor, implements the electricity consumption prediction method provided in the above-described embodiments of the present application.

It will be appreciated by those skilled in the art that the structure shown in fig. 10 is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation of the electricity consumption prediction apparatus to which the present application is applied, and that a specific electricity consumption prediction apparatus may include more or less components than those shown in the drawings, or may combine some components, or have a different arrangement of components.

In one embodiment, there is provided an electricity consumption information prediction apparatus including a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:

acquiring first electric quantity data of a first preset duration;

In one embodiment, the processor when executing the computer program further performs the steps of:

acquiring second electricity consumption data of a second preset duration;

In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:

acquiring first electric quantity data of a first preset duration;

In one embodiment, the computer program when executed by the processor further performs the steps of:

acquiring second electricity consumption data of a second preset duration;

In one embodiment, a computer program product is provided comprising a computer program which, when executed by a processor, performs the steps of:

acquiring first electric quantity data of a first preset duration;

acquiring second electricity consumption data of a second preset duration;

Those skilled in the art will appreciate that implementing all or part of the above-described methods may be accomplished by way of a computer program, which may be stored on a non-transitory computer readable storage medium and which, when executed, may comprise the steps of the above-described embodiments of the methods. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The foregoing examples represent only a few embodiments of the present application, which are described in more detail and are not thereby to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.

Claims

1. A method of power consumption prediction, the method comprising:

acquiring first electric quantity data of a first preset duration;

and predicting the electricity consumption increase rate corresponding to a second preset duration through the electricity consumption prediction model based on the first electricity consumption data, and predicting the whole society electricity consumption information corresponding to the second preset duration according to the first electricity consumption data and the electricity consumption increase rate.

2. The method of claim 1, wherein the social electricity usage information includes a social electricity usage amount and a social electricity usage rate, and the predicting the social electricity usage information corresponding to the second preset duration from the first electricity usage amount data and the electricity usage rate includes:

predicting the whole society electricity consumption by the electricity consumption prediction model based on the first electricity consumption data and the electricity consumption increase rate;

and predicting the social electricity utilization rate through the electricity prediction model based on the first electricity consumption data and the social electricity consumption.

3. The method of claim 1, wherein predicting, based on the first power data, a power usage rate increase corresponding to a second preset duration through the power prediction model, comprises:

and predicting the power consumption increase rate corresponding to the second preset duration through the power prediction model based on the first prediction elastic coefficient.

4. A method according to any one of claims 1-3, characterized in that the method further comprises:

acquiring second electricity consumption data of the second preset duration;

And updating the electric quantity prediction model according to the second electric quantity data, the electric quantity increase rate corresponding to the second preset duration and the whole society electric quantity information.

5. A method according to any one of claims 1-3, wherein the training method of the preset electrical quantity prediction model comprises:

training an initial electric quantity prediction model according to the first historical electric quantity data to obtain the preset electric quantity prediction model.

6. The method of claim 5, wherein the method for constructing the initial power prediction model comprises:

and constructing the initial electric quantity prediction model according to the second preset elastic coefficient and the second historical electric quantity data.

7. The method of claim 6, wherein said determining a second predicted spring rate based on said second historical power usage data and said historical power impact data comprises:

Dividing the second historical electricity consumption data and the historical electricity consumption influence factor data of the fourth preset duration into sub-historical electricity consumption data and sub-historical electricity consumption influence factor data of a plurality of sub-time periods;

for each sub-time period, determining a bullet coefficient of the sub-time period according to the sub-historical electricity consumption data of the sub-time period and the sub-historical electricity influence factor data;

and determining the second predicted elasticity coefficient according to the bullet elasticity coefficient of each sub-time period.

8. An electricity consumption information prediction apparatus, characterized in that the apparatus comprises:

the prediction module is used for predicting the electricity consumption increase rate corresponding to a second preset duration through the electricity consumption prediction model based on the first electricity consumption data, and predicting the whole society electricity consumption information corresponding to the second preset duration according to the first electricity consumption data and the electricity consumption increase rate.

9. Electricity consumption information prediction device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.

11. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.